© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 7345
    Prev
    Next
    INDEX
    Explanations

    first followed by common phrases

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron detects occurrences of the ordinal “first.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    на
    1.55
    个
    1.36
    AZIONE
    1.35
    冫
    1.27
    ー
    1.24
    RE
    1.17
    c
    1.17
    re
    1.16
    ↡
    1.16
    년에
    1.15
    POSITIVE LOGITS
     tranche
    1.27
     baseman
    1.24
     responders
    1.14
     generation
    1.13
     glimpse
    1.13
     pagk
    1.09
     responder
    1.09
     iteration
    1.08
     recitation
    1.02
     impression
    1.02
    Activations Density 0.087%

    No Known Activations